Spike-Timing-Dependent Plasticity for Bernoulli Message Passing

TL;DR

This paper introduces a biologically plausible spiking neural network model that performs Bayesian inference via message passing for Bernoulli messages, trained with spike-timing-dependent plasticity, and demonstrates its effectiveness on coding theory tasks.

Contribution

It presents a novel integration of spike-timing-dependent plasticity with message passing algorithms for Bayesian inference in spiking neural networks.

Findings

Network performance closely matches numerical solutions.

Successfully applied to coding theory example.

Demonstrates versatility in signal transmission tasks.

Abstract

Bayesian inference provides a principled framework for understanding brain function, while neural activity in the brain is inherently spike-based. This paper bridges these two perspectives by designing spiking neural networks that simulate Bayesian inference through message passing for Bernoulli messages. To train the networks, we employ spike-timing-dependent plasticity, a biologically plausible mechanism for synaptic plasticity which is based on the Hebbian rule. Our results demonstrate that the network's performance closely matches the true numerical solution. We further demonstrate the versatility of our approach by implementing a factor graph example from coding theory, illustrating signal transmission over an unreliable channel.